Decoding¶

Decoding and encoding, including machine learning and receptive fields.

`CSP`([n_components, reg, log, cov_est, …])	M/EEG signal decomposition using the Common Spatial Patterns (CSP).
`EMS`()	Transformer to compute event-matched spatial filters.
`FilterEstimator`(info, l_freq, h_freq[, …])	Estimator to filter RtEpochs.
`LinearModel`([model])	Compute and store patterns from linear models.
`PSDEstimator`([sfreq, fmin, fmax, bandwidth, …])	Compute power spectral density (PSD) using a multi-taper method.
`Scaler`([info, scalings, with_mean, with_std])	Standardize channel data.
`TemporalFilter`([l_freq, h_freq, sfreq, …])	Estimator to filter data array along the last dimension.
`TimeFrequency`(freqs[, sfreq, method, …])	Time frequency transformer.
`UnsupervisedSpatialFilter`(estimator[, average])	Use unsupervised spatial filtering across time and samples.
`Vectorizer`()	Transform n-dimensional array into 2D array of n_samples by n_features.
`ReceptiveField`(tmin, tmax, sfreq[, …])	Fit a receptive field model.
`TimeDelayingRidge`(tmin, tmax, sfreq[, …])	Ridge regression of data with time delays.
`SlidingEstimator`(base_estimator[, scoring, …])	Search Light.
`GeneralizingEstimator`(base_estimator[, …])	Generalization Light.
`SPoC`([n_components, reg, log, …])	Implementation of the SPoC spatial filtering.
`SSD`(info, filt_params_signal, filt_params_noise)	M/EEG signal decomposition using the Spatio-Spectral Decomposition (SSD).

Functions that assist with decoding and model fitting:

`compute_ems`(epochs[, conditions, picks, …])	Compute event-matched spatial filter on epochs.
`cross_val_multiscore`(estimator, X[, y, …])	Evaluate a score by cross-validation.
`get_coef`(estimator[, attr, inverse_transform])	Retrieve the coefficients of an estimator ending with a Linear Model.